© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14381
    Prev
    Next
    INDEX
    Explanations

    self-perception and appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.10
     Heller
    -0.10
     myself
    -0.09
     ourselves
    -0.09
    ENT
    -0.09
    och
    -0.09
     Capt
    -0.09
     footprint
    -0.08
     himself
    -0.08
    uche
    -0.08
    POSITIVE LOGITS
    InThe
    0.11
     overload
    0.10
    ç©
    0.10
     owed
    0.10
    phis
    0.09
     clad
    0.09
     naked
    0.09
    azon
    0.09
     Olson
    0.09
     pix
    0.09
    Activations Density 0.006%

    No Known Activations